fix(huggingface): avoid hf api calls when using local HuggingFaceEndpoint#35633
Merged
ccurme (ccurme) merged 2 commits intolangchain-ai:masterfrom Mar 29, 2026
Conversation
Darshan Gorasiya (dv-gorasiya)
requested review from
ccurme (ccurme) and
Mason Daugherty (mdrxy)
as code owners
github-actions
Bot
added
integration
…oint When endpoint_url is a local or custom URL we don't pass the HF API token to the inference client so it doesn't try to hit Hugging Face (fixes 401/404 and egress on air-gapped systems). Fixes langchain-ai#30333.
Darshan Gorasiya (dv-gorasiya)
force-pushed
the
fix/huggingface-local-endpoint-no-egress-30333
branch
from
d67b0ec to
3737fc8
Compare
Contributor
Author
|
Related: Dev Patel (@Devpatel1901) and others discussed this on the issue. A detailed workaround/solution was also shared last year here: Solution (TGI/local endpoint). This PR implements the fix in langchain-huggingface so local |
ccurme (ccurme)
approved these changes
Mar 29, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
When HuggingFaceEndpoint is used with a local/custom endpoint_url (e.g. TGI on localhost), we don't pass the HF API token into the inference client so it doesn't try to hit Hugging Face. Fixes #30333.